© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 94036
    Prev
    Next
    INDEX
    Explanations

    expressions of honesty and frankness in statements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    na
    -0.08
    aver
    -0.07
    men
    -0.06
     Official
    -0.06
    âĢı
    -0.06
    pd
    -0.06
     somehow
    -0.06
    rous
    -0.06
    531
    -0.06
    mar
    -0.06
    POSITIVE LOGITS
    iyel
    0.07
    upp
    0.07
    atoire
    0.07
    LTR
    0.07
    anchors
    0.07
    UPI
    0.07
    ewis
    0.07
    оже
    0.07
    ifax
    0.07
    heits
    0.07
    Activations Density 0.008%

    No Known Activations